Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to violence or injury dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¬
    -0.17
     Bulk
    -0.17
    attles
    -0.16
    иÑģк
    -0.15
    imple
    -0.15
    Bulk
    -0.15
    ctors
    -0.15
    laÄį
    -0.15
     Wheels
    -0.14
    pectrum
    -0.14
    POSITIVE LOGITS
     blow
    0.50
     blows
    0.45
     Blow
    0.41
     punch
    0.33
     punches
    0.33
     wal
    0.27
     knockout
    0.26
     sucker
    0.25
     Punch
    0.25
     j
    0.23
    Act Density 0.091%

    No Known Activations